Настройки

Укажите год
-

Небесная энциклопедия

Космические корабли и станции, автоматические КА и методы их проектирования, бортовые комплексы управления, системы и средства жизнеобеспечения, особенности технологии производства ракетно-космических систем

Подробнее
-

Мониторинг СМИ

Мониторинг СМИ и социальных сетей. Сканирование интернета, новостных сайтов, специализированных контентных площадок на базе мессенджеров. Гибкие настройки фильтров и первоначальных источников.

Подробнее

Форма поиска

Поддерживает ввод нескольких поисковых фраз (по одной на строку). При поиске обеспечивает поддержку морфологии русского и английского языка
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Укажите год
Укажите год
Применить Всего найдено 24. Отображено 24.
14-01-2021 дата публикации

Systems and Methods for Generating Motion Forecast Data for a Plurality of Actors with Respect to an Autonomous Vehicle

Номер: US20210009166A1
Автор: Li Lingyun, LIANG MING, Ren Mengye, Segal Sean, Urtasun Raquel, YANG Bin, Zeng Wenyuan
Принадлежит:

A computing system can be configured to input data that describes sensor data into an object detection model and receive, as an output of the object detection model, object detection data describing features of the plurality of the actors relative to the autonomous vehicle. The computing system can generate an input sequence that describes the object detection data. The computing system can analyze the input sequence using an interaction model to produce, as an output of the interaction model, an attention embedding with respect to the plurality of actors. The computing system can be configured to input the attention embedding into a recurrent model and determine respective trajectories for the plurality of actors based on motion forecast data received as an output of the recurrent model. 1. A computing system , comprising:an object detection model configured to receive an input representation that describes sensor data, and in response to receipt of the input representation that describes the sensor data, output object detection data describing features of a plurality of actors relative to an autonomous vehicle;an interaction model configured to receive an input sequence that describes the object detection data, and in response to receipt of the input sequence, generate an attention embedding with respect to the plurality of actors;a recurrent model configured to receive the attention embedding, and in response to receipt of the attention embedding, generate motion forecast data with respect to the plurality of actors, the motion forecast data describing respective trajectories for the plurality of actors;a memory that stores a set of instructions; input the input representation that describes the sensor data into the object detection model;', 'receive, as an output of the object detection model, the object detection data describing the features of the plurality of the actors relative to the autonomous vehicle;', 'generate an input sequence that describes the ...

Подробнее
Номер записи: 1
14-01-2021 дата публикации

Systems and Methods for Identifying Unknown Instances

Номер: US20210012116A1
Автор: Kelvin Ka Wing WONG, Mengye Ren, Ming Liang, Raquel Urtasun, Shenlong Wang
Принадлежит: Uatc LLC, Uber Technologies Inc

Systems and methods of the present disclosure provide an improved approach for open-set instance segmentation by identifying both known and unknown instances in an environment. For example, a method can include receiving sensor point cloud input data including a plurality of three-dimensional points. The method can include determining a feature embedding and at least one of an instance embedding, class embedding, and/or background embedding for each of the plurality of three-dimensional points. The method can include determining a first subset of points associated with one or more known instances within the environment based on the class embedding and the background embedding associated with each point in the plurality of points. The method can include determining a second subset of points associated with one or more unknown instances within the environment based on the first subset of points. The method can include segmenting the input data into known and unknown instances.

Подробнее
Номер записи: 2
03-02-2022 дата публикации

Systems and Methods for Mitigating Vehicle Pose Error Across an Aggregated Feature Map

Номер: US20220032970A1
Автор: Ren Mengye, Tu Xuanyuan, Urtasun Raquel, Vadivelu Nicholas Baskar, WANG Jingkang
Принадлежит:

Systems and methods for improved vehicle-to-vehicle communications are provided. A system can obtain sensor data depicting its surrounding environment and input the sensor data (or processed sensor data) to a machine-learned model to perceive its surrounding environment based on its location within the environment. The machine-learned model can generate an intermediate environmental representation that encodes features within the surrounding environment. The system can receive a number of different intermediate environmental representations and corresponding locations from various other systems, aggregate the representations based on the corresponding locations, and perceive its surrounding environment based on the aggregated representations. The system can determine relative poses between the each of the systems and an absolute pose for each system based on the representations. Each representation can be aggregated based on the relative or absolute poses of each system and weighted according to an estimated accuracy of the location corresponding to the representation. 1. A computer-implemented method , the method comprising:obtaining, by a computing system comprising one or more computing devices onboard an autonomous vehicle, sensor data associated with an environment of a first autonomous vehicle;obtaining, by the computing system, estimated location data indicative of a first estimated pose of the first autonomous vehicle;determining, by the computing system, a first intermediate environmental representation of at least a first portion of the environment of the first autonomous vehicle based, at least in part, on the sensor data;obtaining, by the computing system, a first message from a second autonomous vehicle, wherein the first message comprises a second intermediate environmental representation of at least a second portion of the environment of the first autonomous vehicle and second estimated location data indicative of a second estimated pose of the second ...

Подробнее
Номер записи: 3
16-05-2019 дата публикации

Sparse Convolutional Neural Networks

Номер: US20190146497A1
Автор: Andrei Pokrovsky, Bin Yang, Mengye Ren, Raquel Urtasun
Принадлежит: Uber Technologies Inc

The present disclosure provides systems and methods that apply neural networks such as, for example, convolutional neural networks, to sparse imagery in an improved manner. For example, the systems and methods of the present disclosure can be included in or otherwise leveraged by an autonomous vehicle. In one example, a computing system can extract one or more relevant portions from imagery, where the relevant portions are less than an entirety of the imagery. The computing system can provide the relevant portions of the imagery to a machine-learned convolutional neural network and receive at least one prediction from the machine-learned convolutional neural network based at least in part on the one or more relevant portions of the imagery. Thus, the computing system can skip performing convolutions over regions of the imagery where the imagery is sparse and/or regions of the imagery that are not relevant to the prediction being sought.

Подробнее
Номер записи: 4
01-07-2021 дата публикации

Jointly Learnable Behavior and Trajectory Planning for Autonomous Vehicles

Номер: US20210200212A1
Автор: Lin Yen-Chen, Pokrovsky Andrei, Ren Mengye, Sadat Abbas, Urtasun Raquel, Yumer Ersin
Принадлежит:

Systems and methods for generating motion plans for autonomous vehicles are provided. An autonomous vehicle can include a machine-learned motion planning system including one or more machine-learned models configured to generate target trajectories for the autonomous vehicle. The model(s) include a behavioral planning stage configured to receive situational data based at least in part on the one or more outputs of the set of sensors and to generate behavioral planning data based at least in part on the situational data and a unified cost function. The model(s) includes a trajectory planning stage configured to receive the behavioral planning data from the behavioral planning stage and to generate target trajectory data for the autonomous vehicle based at least in part on the behavioral planning data and the unified cost function. 1. An autonomous vehicle , comprising:a set of sensors configured to generate one or more outputs based at least in part on an environment external to the autonomous vehicle;one or more processors; and [ a behavioral planning stage configured to receive situational data based at least in part on the one or more outputs of the set of sensors and to generate behavioral planning data based at least in part on the situational data and a unified cost function; and', 'a trajectory planning stage configured to receive the behavioral planning data from the behavioral planning stage and to generate target trajectory data for the autonomous vehicle based at least in part on the behavioral planning data and the unified cost function; and, 'a machine-learned motion planning system comprising one or more machine-learned models configured to generate target trajectories for the autonomous vehicle, the machine-learned motion planning system comprising, obtaining the situational data associated with the environment external to the autonomous vehicle:', 'generating, using the behavioral planning stage of the machine-learned motion planning system, ...

Подробнее
Номер записи: 5
12-08-2021 дата публикации

Systems and Methods for Optimized Multi-Agent Routing Between Nodes

Номер: US20210248460A1
Автор: Ren Mengye, Sykora Quinlan, Urtasun Raquel
Принадлежит:

A computing system can be configured to generate, for an autonomous vehicle, a route through a transportation network comprising a plurality of segments. The method can include receiving sets of agent attention data from additional autonomous vehicles that are respectively currently located at one or more other segments of the transportation network. The method can include inputting the sets of agent attention data into a value iteration graph neural network that comprises a plurality of nodes that respectively correspond to the plurality of segments of the transportation network. The method can include receiving node values respectively for the segments as an output of the value iteration graph neural network. The method can include selecting a next segment to include in the route for the autonomous vehicle based at least in part on the node values. 1. An autonomous vehicle computing system of a vehicle comprising:one or more processors;a value iteration graph neural network comprising a plurality of nodes that respectively correspond to a plurality of segments of a transportation network, wherein a plurality of node feature vectors respectively correspond to the plurality of nodes; and determining, using the value iteration graph neural network, a first plurality of updated node feature vectors and a first plurality of node values respectively for the plurality of nodes;', 'navigating the vehicle to a first segment of the transportation network based at least in part on the first plurality of node values;', 'receiving, from one or more remote autonomous vehicle computing systems of one or more other vehicles, one or more incoming communication vectors;', 'inputting the one or more incoming communication vectors and the plurality of updated node feature vectors to the value iteration graph neural network to obtain a second plurality of updated node feature vectors and a second plurality of node values; and', 'navigating the vehicle to a second segment of the ...

Подробнее
Номер записи: 6
09-09-2021 дата публикации

Systems and Methods for Selecting Trajectories Based on Interpretable Semantic Representations

Номер: US20210276591A1
Автор: Casas Sergio, Ren Mengye, Sadat Abbas, Urtasun Raquel
Принадлежит:

Systems and methods for generating semantic occupancy maps are provided. In particular, a computing system can obtain map data for a geographic area and sensor data obtained by the autonomous vehicle. The computer system can identify feature data included in the map data and sensor data. The computer system can, for a respective semantic object type from a plurality of semantic object types, determine, by the computing system and using feature data as input to a respective machine-learned model from a plurality of machine-learned models, one or more occupancy maps for one or more timesteps in the future, and wherein the respective machine-learned model is trained to determine occupancy for the respective semantic object type. The computer system can select a trajectory for the autonomous vehicle based on a plurality of occupancy maps associated with the plurality of semantic object types. 1. A computer-implemented method for autonomous vehicle motion control , the method comprising:obtaining, by a computing system including one or more processors, map data for a geographic area and sensor data obtained by the autonomous vehicle;identifying, by the computing system, feature data included in the map data and sensor data;for a respective semantic object type from a plurality of semantic object types, determining, by the computing system and using feature data as input to a respective machine-learned model from a plurality of machine-learned models, one or more occupancy maps for one or more timesteps in the future, and wherein the respective machine-learned model is trained to determine occupancy for the respective semantic object type; andselecting, by the computing system, a trajectory for the autonomous vehicle based on a plurality of occupancy maps associated with the plurality of semantic object types.2. The computer-implemented method of claim 1 , wherein semantic object types are organized into a semantic hierarchy.3. The computer-implemented method of claim 1 , ...

Подробнее
Номер записи: 7
09-09-2021 дата публикации

Systems and Methods for Using Attention Masks to Improve Motion Planning

Номер: US20210278852A1
Автор: Bin Yang, Bob Qingyuan Wei, Mengye Ren, Ming Liang, Raquel Urtasun, Wenyuan Zeng
Принадлежит: Uatc LLC

Systems and methods for generating attention masks are provided. In particular, a computing system can access sensor data and map data for an area around an autonomous vehicle. The computing system can generate a voxel grid representation of the sensor data and map data. The computing system can generate an attention mask based on the voxel grid representation. The computing system can generate, by using the voxel grid representation and the attention mask as input to a machine-learned model, an attention weighted feature map. The computing system can determine using the attention weighted feature map, a planning cost volume for an area around the autonomous vehicle. The computing system can select a trajectory for the autonomous vehicle based, at least in part, on the planning cost volume.

Подробнее
Номер записи: 8
09-09-2021 дата публикации

Systems and Methods for Training Machine-Learned Models with Deviating Intermediate Representations

Номер: US20210279640A1
Автор: Manivasagam Sivabalan, Ren Mengye, Tu Xuanyuan, Urtasun Raquel, WANG Jingkang, Wang Tsu-shuan
Принадлежит:

Systems and methods for vehicle-to-vehicle communications are provided. An adverse system can obtain sensor data representative of an environment proximate to a targeted system. The adverse system can generate an intermediate representation of the environment and a representation deviation for the intermediate representation. The representation deviation can be designed to disrupt a machine-learned model associated with the target system. The adverse system can communicate the intermediate representation modified by the representation deviation to the target system. The target system can train the machine-learned model associated with the target system to detect the modified intermediate representation. Detected modified intermediate representations can be discarded before disrupting the machine-learned model. 1. A computer-implemented method , the method comprising:obtaining, by a computing system comprising one or more computing devices, sensor data representative of a secondary environment proximate to an autonomous vehicle;generating, by the computing system, an intermediate representation for the autonomous vehicle based, at least in part, on the sensor data, wherein the intermediate representation is descriptive of at least a portion of the secondary environment;determining, by the computing system, an intermediate representation deviation for the intermediate representation based, at least in part, on the intermediate representation and a machine-learned model associated with the autonomous vehicle;generating, by the computing system, data indicative of a modified intermediate representation based, at least in part, on the intermediate representation and the intermediate representation deviation; andcommunicating, by the computing system, the data indicative of the modified intermediate representation to a vehicle computing system associated with the autonomous vehicle.2. The computer-implemented method of claim 1 , wherein the machine-learned model ...

Подробнее
Номер записи: 9
17-05-2022 дата публикации

Systems and methods for simulating traffic scenes

Номер: CA3139477A1
Автор: Kelvin Ka Wing WONG, Mengye Ren, Raquel Urtasun, Shenlong Wang, Shuhan Tan, Sivabalan Manivasagam
Принадлежит: Uatc LLC

Example aspects of the present disclosure describe a scene generator for simulating scenes in an environment. For example, snapshots of simulated traffic scenes can be generated by sampling a joint probability distribution trained on real-world trotfic scenes. In some implementations, samples of the joint probability distribution can be obtained by sampling a plurality of factorized probability distributions for a plurality of objects for sequential insertion into the scene.

Подробнее
Номер записи: 10
20-05-2021 дата публикации

Systems and Methods for Generating Motion Forecast Data for a Plurality of Actors with Respect to an Autonomous Vehicle

Номер: US20210146963A1
Автор: Bin Yang, LingYun Li, Mengye Ren, Ming Liang, Raquel Urtasun, Sean Segal, Wenyuan Zeng
Принадлежит: Uatc LLC

A computing system can input first relative location embedding data into an interaction transformer model and receive, as an output of the interaction transformer model, motion forecast data for actors relative to a vehicle. The computing system can input the motion forecast data into a prediction model to receive respective trajectories for the actors for a current time step and respective projected trajectories for the actors for a subsequent time step. The computing system can generate second relative location embedding data based on the respective projected trajectories from the second time step. The computing system can produce second motion forecast data using the interaction transformer model based on the second relative location embedding. The computing system can determine second respective trajectories for the actors using the prediction model based on the second forecast data.

Подробнее
Номер записи: 11
21-10-2021 дата публикации

Sparse Convolutional Neural Networks

Номер: US20210325882A1
Автор: Andrei Pokrovsky, Bin Yang, Mengye Ren, Raquel Urtasun
Принадлежит: Uatc LLC

The present disclosure provides systems and methods that apply neural networks such as, for example, convolutional neural networks, to sparse imagery in an improved manner. For example, the systems and methods of the present disclosure can be included in or otherwise leveraged by an autonomous vehicle. In one example, a computing system can extract one or more relevant portions from imagery, where the relevant portions are less than an entirety of the imagery. The computing system can provide the relevant portions of the imagery to a machine-learned convolutional neural network and receive at least one prediction from the machine-learned convolutional neural network based at least in part on the one or more relevant portions of the imagery. Thus, the computing system can skip performing convolutions over regions of the imagery where the imagery is sparse and/or regions of the imagery that are not relevant to the prediction being sought.

Подробнее
Номер записи: 12
02-01-2024 дата публикации

Sparse convolutional neural networks

Номер: US11860629B2
Автор: Andrei Pokrovsky, Bin Yang, Mengye Ren, Raquel Urtasun
Принадлежит: Uatc LLC

The present disclosure provides systems and methods that apply neural networks such as, for example, convolutional neural networks, to sparse imagery in an improved manner. For example, the systems and methods of the present disclosure can be included in or otherwise leveraged by an autonomous vehicle. In one example, a computing system can extract one or more relevant portions from imagery, where the relevant portions are less than an entirety of the imagery. The computing system can provide the relevant portions of the imagery to a machine-learned convolutional neural network and receive at least one prediction from the machine-learned convolutional neural network based at least in part on the one or more relevant portions of the imagery. Thus, the computing system can skip performing convolutions over regions of the imagery where the imagery is sparse and/or regions of the imagery that are not relevant to the prediction being sought.

Подробнее
Номер записи: 13
11-01-2024 дата публикации

Systems and Methods for Generating Motion Forecast Data for a Plurality of Actors with Respect to an Autonomous Vehicle

Номер: US20240010241A1
Автор: Bin Yang, LingYun Li, Mengye Ren, Ming Liang, Raquel Urtasun Sotil, Sean Segal, Wenyuan Zeng
Принадлежит: Uatc LLC

A computing system can input first relative location embedding data into an interaction transformer model and receive, as an output of the interaction transformer model, motion forecast data for actors relative to a vehicle. The computing system can input the motion forecast data into a prediction model to receive respective trajectories for the actors for a current time step and respective projected trajectories for the actors for a subsequent time step. The computing system can generate second relative location embedding data based on the respective projected trajectories from the second time step. The computing system can produce second motion forecast data using the interaction transformer model based on the second relative location embedding. The computing system can determine second respective trajectories for the actors using the prediction model based on the second forecast data.

Подробнее
Номер записи: 14
09-11-2023 дата публикации

Jointly Learnable Behavior and Trajectory Planning for Autonomous Vehicles

Номер: US20230359202A1
Автор: Abbas Sadat, Andrei Pokrovsky, Ersin Yumer, Mengye Ren, Raquel Urtasun, Yen-Chen Lin
Принадлежит: Uatc LLC

Systems and methods for generating motion plans for autonomous vehicles are provided. An autonomous vehicle can include a machine-learned motion planning system including one or more machine-learned models configured to generate target trajectories for the autonomous vehicle. The model(s) include a behavioral planning stage configured to receive situational data based at least in part on the one or more outputs of the set of sensors and to generate behavioral planning data based at least in part on the situational data and a unified cost function. The model(s) includes a trajectory planning stage configured to receive the behavioral planning data from the behavioral planning stage and to generate target trajectory data for the autonomous vehicle based at least in part on the behavioral planning data and the unified cost function.

Подробнее
Номер записи: 15
05-12-2023 дата публикации

Systems and methods for selecting trajectories based on interpretable semantic representations

Номер: US11834069B2
Автор: Abbas Sadat, Mengye Ren, Raquel Urtasun, Sergio Casas
Принадлежит: Uatc Lcc

Systems and methods for generating semantic occupancy maps are provided. In particular, a computing system can obtain map data for a geographic area and sensor data obtained by the autonomous vehicle. The computer system can identify feature data included in the map data and sensor data. The computer system can, for a respective semantic object type from a plurality of semantic object types, determine, by the computing system and using feature data as input to a respective machine-learned model from a plurality of machine-learned models, one or more occupancy maps for one or more timesteps in the future, and wherein the respective machine-learned model is trained to determine occupancy for the respective semantic object type. The computer system can select a trajectory for the autonomous vehicle based on a plurality of occupancy maps associated with the plurality of semantic object types.

Подробнее
Номер записи: 16
12-09-2023 дата публикации

Jointly learnable behavior and trajectory planning for autonomous vehicles

Номер: US11755014B2
Автор: Abbas Sadat, Andrei Pokrovsky, Ersin Yumer, Mengye Ren, Raquel Urtasun, Yen-Chen Lin
Принадлежит: Uatc LLC

Systems and methods for generating motion plans for autonomous vehicles are provided. An autonomous vehicle can include a machine-learned motion planning system including one or more machine-learned models configured to generate target trajectories for the autonomous vehicle. The model(s) include a behavioral planning stage configured to receive situational data based at least in part on the one or more outputs of the set of sensors and to generate behavioral planning data based at least in part on the situational data and a unified cost function. The model(s) includes a trajectory planning stage configured to receive the behavioral planning data from the behavioral planning stage and to generate target trajectory data for the autonomous vehicle based at least in part on the behavioral planning data and the unified cost function.

Подробнее
Номер записи: 17
10-10-2023 дата публикации

Systems and methods for generating motion forecast data for a plurality of actors with respect to an autonomous vehicle

Номер: US11780472B2
Автор: Bin Yang, LingYun Li, Mengye Ren, Ming Liang, Raquel Urtasun, Sean Segal, Wenyuan Zeng
Принадлежит: Uatc LLC

A computing system can input first relative location embedding data into an interaction transformer model and receive, as an output of the interaction transformer model, motion forecast data for actors relative to a vehicle. The computing system can input the motion forecast data into a prediction model to receive respective trajectories for the actors for a current time step and respective projected trajectories for the actors for a subsequent time step. The computing system can generate second relative location embedding data based on the respective projected trajectories from the second time step. The computing system can produce second motion forecast data using the interaction transformer model based on the second relative location embedding. The computing system can determine second respective trajectories for the actors using the prediction model based on the second forecast data.

Подробнее
Номер записи: 18
26-09-2023 дата публикации

Systems and methods for identifying unknown instances

Номер: US11769058B2
Автор: Kelvin Ka Wing WONG, Mengye Ren, Ming Liang, Raquel Urtasun, Shenlong Wang
Принадлежит: Uatc LLC

Systems and methods of the present disclosure provide an improved approach for open-set instance segmentation by identifying both known and unknown instances in an environment. For example, a method can include receiving sensor point cloud input data including a plurality of three-dimensional points. The method can include determining a feature embedding and at least one of an instance embedding, class embedding, and/or background embedding for each of the plurality of three-dimensional points. The method can include determining a first subset of points associated with one or more known instances within the environment based on the class embedding and the background embedding associated with each point in the plurality of points. The method can include determining a second subset of points associated with one or more unknown instances within the environment based on the first subset of points. The method can include segmenting the input data into known and unknown instances.

Подробнее
Номер записи: 19
04-04-2024 дата публикации

Scaling forward gradient with local optimization

Номер: WO2024073439A1
Автор: Geoffrey Everest Hinton, Mengye Ren, Renjie LIAO, Simon Kornblith
Принадлежит: Google LLC

A plurality of model portions are determined from a machine-learned model based on at least one criterion. A plurality of local optimization functions are respectively determined for the plurality of model portions. Forward-mode differentiation is performed for each model portion of the plurality of model portions. Performing forward-mode differentiation includes applying a perturbation to outputs of one or more model units of the model portion. Performing forward-mode differentiation includes, based at least in part on the perturbation, determining a gradient of the local optimization function for the model portion. Performing forward-mode differentiation includes modifying one or more parameters of the model portion based on the gradient.

Подробнее
Номер записи: 20
16-05-2024 дата публикации

Unsupervised object detection from lidar point clouds

Номер: US20240159871A1
Автор: Angi Joyce YANG, Lunjun ZHANG, Mengye Ren, Raquel Urtasun, Sergio CASAS ROMERO, Yuwen Xiong
Принадлежит: Waabi Innovation Inc

Unsupervised object detection from lidar point clouds includes forecasting a set of new positions of a set of objects in a geographic region based on a first set of object tracks to obtain a set of forecasted object positions, and obtaining a new LiDAR point cloud of the geographic region. A detector model processes the new LiDAR point cloud to obtain a new set of bounding boxes around the set of objects detected in the new LiDAR point cloud. Object detection further includes matching the new set of bounding boxes to the set of forecasted object positions to generate a set of matches, updating the first set of object tracks with the new set of bounding boxes according to the set of matches to obtain an updated set of object tracks, and filtering, after updating, the updated set of object tracks to remove object tracks failing to satisfy a track length threshold, to generate a training set of object tracks. The object detection further includes selecting at least a subset of the new set of bounding boxes that are in the training set of object tracks, and retraining the detector model using the at least the subset of the new set of bounding boxes.

Подробнее
Номер записи: 21
14-03-2024 дата публикации

Sparse Convolutional Neural Networks

Номер: US20240085908A1
Автор: Andrei Pokrovsky, Bin Yang, Mengye Ren, Raquel Urtasun
Принадлежит: Uatc LLC

The present disclosure provides systems and methods that apply neural networks such as, for example, convolutional neural networks, to sparse imagery in an improved manner. For example, the systems and methods of the present disclosure can be included in or otherwise leveraged by an autonomous vehicle. In one example, a computing system can extract one or more relevant portions from imagery, where the relevant portions are less than an entirety of the imagery. The computing system can provide the relevant portions of the imagery to a machine-learned convolutional neural network and receive at least one prediction from the machine-learned convolutional neural network based at least in part on the one or more relevant portions of the imagery. Thus, the computing system can skip performing convolutions over regions of the imagery where the imagery is sparse and/or regions of the imagery that are not relevant to the prediction being sought.

Подробнее
Номер записи: 22
11-05-2024 дата публикации

Insupervised object detection from lidar point clouds

Номер: CA3219820A1
Автор: Anqi Joyce Yang, Lunjun ZHANG, Mengye Ren, Raquel Urtasun, Sergio CASAS ROMERO, Yuwen Xiong
Принадлежит: Waabi Innovation Inc

Unsupervised object detection from lidar point clouds includes forecasting a set of new positions of a set of objects in a geographic region based on a first set of object tracks to obtain a set of forecasted object positions, and obtaining a new LiDAR point cloud of the geographic region. A detector model processes the new LiDAR point cloud to obtain a new set of bounding boxes around the set of objects detected in the new LiDAR point cloud. Object detection further includes matching the new set of bounding boxes to the set of forecasted object positions to generate a set of matches, updating the first set of object tracks with the new set of bounding boxes according to the set of matches to obtain an updated set of object tracks, and filtering, after updating, the updated set of object tracks to remove object tracks failing to satisfy a track length threshold, to generate a training set of object tracks. The object detection further includes selecting at least a subset of the new set of bounding boxes that are in the training set of object tracks, and retraining the detector model using the at least the subset of the new set of bounding boxes.

Подробнее
Номер записи: 23
22-10-2024 дата публикации

Systems and methods for mitigating vehicle pose error across an aggregated feature map

Номер: US12127085B2
Автор: Jingkang Wang, Mengye Ren, Nicholas Baskar Vadivelu, Raquel Urtasun, Xuanyuan Tu
Принадлежит: Aurora Operations Inc

Systems and methods for improved vehicle-to-vehicle communications are provided. A system can obtain sensor data depicting its surrounding environment and input the sensor data (or processed sensor data) to a machine-learned model to perceive its surrounding environment based on its location within the environment. The machine-learned model can generate an intermediate environmental representation that encodes features within the surrounding environment. The system can receive a number of different intermediate environmental representations and corresponding locations from various other systems, aggregate the representations based on the corresponding locations, and perceive its surrounding environment based on the aggregated representations. The system can determine relative poses between the each of the systems and an absolute pose for each system based on the representations. Each representation can be aggregated based on the relative or absolute poses of each system and weighted according to an estimated accuracy of the location corresponding to the representation.

Подробнее
Номер записи: 24